Found 15 bookmarks
Newest
OpenPipe/ART: Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, Kimi, and more!
OpenPipe/ART: Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, Kimi, and more!
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, Kimi, and more! - OpenP...
·github.com·
OpenPipe/ART: Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, Kimi, and more!
Build internal tools, remarkably fast.
Build internal tools, remarkably fast.
Retool is the fast way to build internal tools. Drag-and-drop our building blocks and connect them to your databases and APIs to build your own tools, instantly. Connects with Postgres, REST APIs, GraphQL, Firebase, Google Sheets, and more. Built by developers, for developers. Trusted by startups and Fortune 500s. Sign up for free.
·retool.com·
Build internal tools, remarkably fast.